
#!wget https://onlineacademiccommunity.uvic.ca/isot/wp-content/uploads/sites/7295/2023/03/News-_dataset.zip


#!unzip -o News-_dataset.zip


import pandas as pd


df_fake = pd.read_csv("Fake.csv")


df_fake


df_fake["fake"] = True


df_fake


df_non_fake = pd.read_csv("True.csv")


df_non_fake["fake"] = False


df = pd.concat([df_non_fake, df_fake])

df


df.describe()


df[df["text"].duplicated()].sort_values(by="text")


df["text_length"] = df["text"].apply(len)


df["text_length"].describe()

count    44898.000000
mean      2469.109693
std       2171.617091
min          1.000000
25%       1234.000000
50%       2186.000000
75%       3105.000000
max      51794.000000
Name: text_length, dtype: float64


df = df[df["text_length"] >= 100]

df


df[df["text"].duplicated(keep=False)].sort_values(by="text")


df_cleaned = df.drop_duplicates(subset="text", keep="first")


df_cleaned["text"].duplicated().sum()

0


df_cleaned[df_cleaned["fake"] == True].count()

title          17157
text           17157
subject        17157
date           17157
fake           17157
text_length    17157
dtype: int64


df_cleaned[df_cleaned["fake"] == False].count()

title          21191
text           21191
subject        21191
date           21191
fake           21191
text_length    21191
dtype: int64


df_cleaned[df_cleaned["fake"] == False].groupby(by="subject").count()


df_cleaned[df_cleaned["fake"] == True].groupby(by="subject").count()


# Transform "fake" labels to fake = 1, not-fake = 0
df_cleaned["fake"] = df_cleaned["fake"].replace(to_replace=False, value=0)
df_cleaned["fake"] = df_cleaned["fake"].replace(to_replace=True, value=1)

/tmp/ipykernel_78769/1935809760.py:2: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df_cleaned["fake"] = df_cleaned["fake"].replace(to_replace=False, value=0)
/tmp/ipykernel_78769/1935809760.py:3: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df_cleaned["fake"] = df_cleaned["fake"].replace(to_replace=True, value=1)


df_cleaned


from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.tree import DecisionTreeClassifier
from sklearn import tree


# Split the dataset into training and testing sets
train_data, test_data, train_labels, test_labels = train_test_split(df_cleaned['text'], df_cleaned['fake'], test_size=0.2, random_state=15)

# Create a TF-IDF vectorizer to convert text into numerical features
vectorizer = TfidfVectorizer(max_features=5000)
train_features = vectorizer.fit_transform(train_data)
test_features = vectorizer.transform(test_data)

# Train a decision tree classifier
tree_model = DecisionTreeClassifier()
tree_model.fit(train_features, train_labels)

# Extract feature names from the vectorizer
feature_names = vectorizer.get_feature_names_out()

# Visualize the decision tree
tree.plot_tree(tree_model, feature_names=feature_names)

# Get the most important features for classification
importance = tree_model.feature_importances_
important_features = [(feature_names[i], importance[i]) for i in range(len(feature_names))]
important_features.sort(key=lambda x: x[1], reverse=True)

# Print the top 10 important features
print("Top 10 important features:")
for feature, importance in important_features[:10]:
    print(f"{feature}: {importance}")

Top 10 important features:
reuters: 0.9737763559972235
getty: 0.005966230401874472
image: 0.0019986892792346893
21wire: 0.0019524007710381203
via: 0.0010386570095431342
obama: 0.0009606127209026892
zika: 0.0007863500518846811
group: 0.00048198222170253165
hillary: 0.00047331728474720217
patrol: 0.00036966585166126775


train_data

21078    If you can t get an acting role in Hollywood, ...
17856    NAIROBI (Reuters) - Kenyan opposition leader R...
6624     NEW YORK (Reuters) - The FBI acted inappropria...
6258     Donald Trump has been getting heavy media cove...
2012     The following statements were posted to the ve...
                               ...                        
9221     The exclusive below from Fox news skips the fa...
14890    // <![CDATA[ (function(d, s, id) { var js, fjs...
2706     MONTEREY, Calif. (Reuters) - The California Pu...
8123     WASHINGTON (Reuters) - U.S. Republican preside...
7670     WASHINGTON (Reuters) - A bipartisan group of l...
Name: text, Length: 30678, dtype: object


pred = tree_model.predict(test_features)


import numpy as np


print("RMS: %r " % np.sqrt(np.mean((pred - test_labels) ** 2)))

RMS: 0.07130740328122925


loc_test_labels = test_labels.reset_index()
sum_correct = 0
for i in range(0, len(pred)-1):
    if pred[i] == loc_test_labels["fake"][i]:
        sum_correct += 1


sum_correct

7630


len(pred)

7670


sum_correct / len(pred) # 99.5% items predicted positively in total

0.9947848761408083


df_cleaned


df_cleaned["text"] = df_cleaned["text"].map(lambda x: x.replace("(Reuters)", ""))

/tmp/ipykernel_78769/2126419442.py:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df_cleaned["text"] = df_cleaned["text"].map(lambda x: x.replace("(Reuters)", ""))


df_cleaned["text"] = df_cleaned["text"].map(lambda x: x.replace("Reuters", ""))

/tmp/ipykernel_78769/3751951457.py:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df_cleaned["text"] = df_cleaned["text"].map(lambda x: x.replace("Reuters", ""))


df_cleaned["text"] = df_cleaned["text"].map(lambda x: x.replace("reuters", ""))

/tmp/ipykernel_78769/4158596274.py:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df_cleaned["text"] = df_cleaned["text"].map(lambda x: x.replace("reuters", ""))


df_cleaned


from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.tree import DecisionTreeClassifier
from sklearn import tree


# Split the dataset into training and testing sets
train_data, test_data, train_labels, test_labels = train_test_split(df_cleaned['text'], df_cleaned['fake'], test_size=0.2, random_state=15)

# Create a TF-IDF vectorizer to convert text into numerical features
vectorizer = TfidfVectorizer(max_features=5000)
train_features = vectorizer.fit_transform(train_data)
test_features = vectorizer.transform(test_data)

# Train a decision tree classifier
tree_model = DecisionTreeClassifier()
tree_model.fit(train_features, train_labels)

# Extract feature names from the vectorizer
feature_names = vectorizer.get_feature_names_out()

# Visualize the decision tree
tree.plot_tree(tree_model, feature_names=feature_names)

# Get the most important features for classification
importance = tree_model.feature_importances_
important_features = [(feature_names[i], importance[i]) for i in range(len(feature_names))]
important_features.sort(key=lambda x: x[1], reverse=True)

# Print the top 10 important features
print("Top 10 important features:")
for feature, importance in important_features[:10]:
    print(f"{feature}: {importance}")

Top 10 important features:
via: 0.3736217156491609
said: 0.22057425618473947
you: 0.03710482407092774
read: 0.03469160153895598
featured: 0.024043081111359076
on: 0.019710078950901183
pic: 0.01886471493556264
this: 0.01678746515061844
https: 0.010358756509108275
com: 0.010351598843464656


pred = tree_model.predict(test_features)

loc_test_labels = test_labels.reset_index()
sum_correct = 0
for i in range(0, len(pred)-1):
    if pred[i] == loc_test_labels["fake"][i]:
        sum_correct += 1


sum_correct / len(pred) # 93.5% items predicted positively in total

0.9323337679269883


df.iloc[5,1]

'WEST PALM BEACH, Fla./WASHINGTON (Reuters) - The White House said on Friday it was set to kick off talks next week with Republican and Democratic congressional leaders on immigration policy, government spending and other issues that need to be wrapped up early in the new year. The expected flurry of legislative activity comes as Republicans and Democrats begin to set the stage for midterm congressional elections in November. President Donald Trump’s Republican Party is eager to maintain control of Congress while Democrats look for openings to wrest seats away in the Senate and the House of Representatives. On Wednesday, Trump’s budget chief Mick Mulvaney and legislative affairs director Marc Short will meet with Senate Majority Leader Mitch McConnell and House Speaker Paul Ryan - both Republicans - and their Democratic counterparts, Senator Chuck Schumer and Representative Nancy Pelosi, the White House said. That will be followed up with a weekend of strategy sessions for Trump, McConnell and Ryan on Jan. 6 and 7 at the Camp David presidential retreat in Maryland, according to the White House. The Senate returns to work on Jan. 3 and the House on Jan. 8. Congress passed a short-term government funding bill last week before taking its Christmas break, but needs to come to an agreement on defense spending and various domestic programs by Jan. 19, or the government will shut down. Also on the agenda for lawmakers is disaster aid for people hit by hurricanes in Puerto Rico, Texas and Florida, and by wildfires in California. The House passed an $81 billion package in December, which the Senate did not take up. The White House has asked for a smaller figure, $44 billion. Deadlines also loom for soon-to-expire protections for young adult immigrants who entered the country illegally as children, known as “Dreamers.” In September, Trump ended Democratic former President Barack Obama’s Deferred Action for Childhood Arrivals (DACA) program, which protected Dreamers from deportation and provided work permits, effective in March, giving Congress until then to devise a long-term solution. Democrats, some Republicans and a number of large companies have pushed for DACA protections to continue. Trump and other Republicans have said that will not happen without Congress approving broader immigration policy changes and tougher border security. Democrats oppose funding for a wall promised by Trump along the U.S.-Mexican border.  “The Democrats have been told, and fully understand, that there can be no DACA without the desperately needed WALL at the Southern Border and an END to the horrible Chain Migration & ridiculous Lottery System of Immigration etc,” Trump said in a Twitter post on Friday. Trump wants to overhaul immigration rules for extended families and others seeking to live in the United States. Republican U.S. Senator Jeff Flake, a frequent critic of the president, said he would work with Trump to protect Dreamers. “We can fix DACA in a way that beefs up border security, stops chain migration for the DREAMers, and addresses the unfairness of the diversity lottery. If POTUS (Trump) wants to protect these kids, we want to help him keep that promise,” Flake wrote on Twitter. Congress in early 2018 also must raise the U.S. debt ceiling to avoid a government default. The U.S. Treasury would exhaust all of its borrowing options and run dry of cash to pay its bills by late March or early April if Congress does not raise the debt ceiling before then, according to the nonpartisan Congressional Budget Office. Trump, who won his first major legislative victory with the passage of a major tax overhaul this month, has also promised a major infrastructure plan. '


df[df['text'].str.contains(' via ')]["text"].iloc[10]

'BEIJING (Reuters) - U.S. President Donald Trump went around and over the “Great Firewall” of China in a late-night tweet in Beijing as he thanked his hosts for a rare tour of the Forbidden City and a private dinner at the sprawling, centuries-old palace complex.  Many Western social media platforms such as Twitter and Facebook are banned in China. A sophisticated system has been built to deny online users within China access to blocked content.  That was not an issue for Trump, known for tweeting to his 42.3 million followers at any hour of the day, on Wednesday, the day he arrived in Beijing. “On behalf of @FLOTUS Melania and I, THANK YOU for an unforgettable afternoon and evening at the Forbidden City in Beijing, President Xi and Madame Peng Liyuan. We are looking forward to rejoining you tomorrow morning!” Trump even changed his Twitter banner, uploading a photograph of himself and Melania with Chinese President Xi Jinping and his wife, Peng Liyuan, during a Chinese opera performance at the Forbidden City.  The Twitter banner upload did not go unnoticed by Chinese state media, with state broadcaster CCTV flashing screenshots of the photograph on Thursday. Trump’s visit was also the third-most talked-about topic on Chinese social media platform Weibo over the last 24 hours, trailing only the birthday of a singer in a Chinese boy band and a weekly Asian pop song chart.  Many people wondered how Trump managed to evade China’s tough internet controls.  “I guess he must have done it via wifi on a satellite network,” said a user on Weibo. Many foreigners log on to virtual private networks (VPNs) to access content hosted outside of China. Another option is to sign up for a data-roaming service before leaving one’s home country.  “The president will tweet whatever he wants. That’s his way of communicating directly with the American people. Why not?” a White House official said ahead of Trump’s arrival in Beijing on Wednesday.  When asked whether China considers Trump’s use of Twitter to be in breach of Chinese law, Foreign Ministry spokeswoman Hua Chunying said there were many means of communication with “the outside world”.  “In China, people have many channels to communicate, it’s just that they communicate in different ways,” Hua said at a regular ministry briefing. “For example, some people use WeChat, some people use Weibo. Some people use Apple phones, some people use Huawei phones.” Trump tweeted again on Thursday afternoon, posting an ABC News video montage of the “incredible” welcome parade at the Great Hall of the People, where he was greeted by a military band and jumping, flag-waving children.  In his tweet, Trump embedded a link to a photograph of his Beijing visit on Instagram - also forbidden in China.  Not all of Trump’s tweets in China were bright and cheerful.  “NoKo has interpreted America’s past restraint as weakness,” he tweeted about reclusive North Korea’s nuclear and missile threats. “This would be a fatal miscalculation. Do not underestimate us. AND DO NOT TRY US.”  '


df_cleaned["text"]

0        WASHINGTON  - The head of a conservative Repub...
1        WASHINGTON  - Transgender people will be allow...
2        WASHINGTON  - The special counsel investigatio...
3        WASHINGTON  - Trump campaign adviser George Pa...
4        SEATTLE/WASHINGTON  - President Donald Trump c...
                               ...                        
22698    21st Century Wire says All the world s a stage...
22699      Randy Johnson 21st Century WireThe majority ...
22700    Tune in to the Alternate Current Radio Network...
22701    21st Century Wire says A new front has just op...
22702    21st Century Wire says It s not that far away....
Name: text, Length: 38348, dtype: object


# Split the dataset into training and testing sets
train_data, test_data, train_labels, test_labels = train_test_split(df_cleaned['text'], df_cleaned['fake'], test_size=0.2, random_state=15)

# Create a TF-IDF vectorizer to convert text into numerical features
vectorizer = TfidfVectorizer(max_features=5000, stop_words='english')
train_features = vectorizer.fit_transform(train_data)
test_features = vectorizer.transform(test_data)

# Train a decision tree classifier
tree_model = DecisionTreeClassifier()
tree_model.fit(train_features, train_labels)

# Extract feature names from the vectorizer
feature_names = vectorizer.get_feature_names_out()

# Visualize the decision tree
tree.plot_tree(tree_model, feature_names=feature_names)

# Get the most important features for classification
importance = tree_model.feature_importances_
important_features = [(feature_names[i], importance[i]) for i in range(len(feature_names))]
important_features.sort(key=lambda x: x[1], reverse=True)

# Print the top 10 important features
print("Top 10 important features:")
for feature, importance in important_features[:10]:
    print(f"{feature}: {importance}")

Top 10 important features:
said: 0.36459215533943434
image: 0.18162157269770549
read: 0.038377607455185106
minister: 0.028863064188978608
washington: 0.02378511619609676
just: 0.02144585968585312
pic: 0.01743437871586469
com: 0.015059904951823782
didn: 0.014563184290509245
https: 0.00940473852375553


pred = tree_model.predict(test_features)

loc_test_labels = test_labels.reset_index()
sum_correct = 0
for i in range(0, len(pred)-1):
    if pred[i] == loc_test_labels["fake"][i]:
        sum_correct += 1


sum_correct / len(pred) # 92.6% items predicted positively in total

0.9245110821382008


from nltk.stem.porter import *

stemmer = PorterStemmer()

df_cleaned["text_stemmed"] = df_cleaned['text'].apply(lambda x: ' '.join([stemmer.stem(word) for word in x.split()]))

/tmp/ipykernel_78769/3504799208.py:5: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df_cleaned["text_stemmed"] = df_cleaned['text'].apply(lambda x: ' '.join([stemmer.stem(word) for word in x.split()]))


df_cleaned["text"].iloc[1]

'WASHINGTON  - Transgender people will be allowed for the first time to enlist in the U.S. military starting on Monday as ordered by federal courts, the Pentagon said on Friday, after President Donald Trump’s administration decided not to appeal rulings that blocked his transgender ban. Two federal appeals courts, one in Washington and one in Virginia, last week rejected the administration’s request to put on hold orders by lower court judges requiring the military to begin accepting transgender recruits on Jan. 1. A Justice Department official said the administration will not challenge those rulings. “The Department of Defense has announced that it will be releasing an independent study of these issues in the coming weeks. So rather than litigate this interim appeal before that occurs, the administration has decided to wait for DOD’s study and will continue to defend the president’s lawful authority in District Court in the meantime,” the official said, speaking on condition of anonymity. In September, the Pentagon said it had created a panel of senior officials to study how to implement a directive by Trump to prohibit transgender individuals from serving. The Defense Department has until Feb. 21 to submit a plan to Trump. Lawyers representing currently-serving transgender service members and aspiring recruits said they had expected the administration to appeal the rulings to the conservative-majority Supreme Court, but were hoping that would not happen. Pentagon spokeswoman Heather Babb said in a statement: “As mandated by court order, the Department of Defense is prepared to begin accessing transgender applicants for military service Jan. 1. All applicants must meet all accession standards.” Jennifer Levi, a lawyer with gay, lesbian and transgender advocacy group GLAD, called the decision not to appeal “great news.” “I’m hoping it means the government has come to see that there is no way to justify a ban and that it’s not good for the military or our country,” Levi said. Both GLAD and the American Civil Liberties Union represent plaintiffs in the lawsuits filed against the administration. In a move that appealed to his hard-line conservative supporters, Trump announced in July that he would prohibit transgender people from serving in the military, reversing Democratic President Barack Obama’s policy of accepting them. Trump said on Twitter at the time that the military “cannot be burdened with the tremendous medical costs and disruption that transgender in the military would entail.” Four federal judges - in Baltimore, Washington, D.C., Seattle and Riverside, California - have issued rulings blocking Trump’s ban while legal challenges to the Republican president’s policy proceed. The judges said the ban would likely violate the right under the U.S. Constitution to equal protection under the law. The Pentagon on Dec. 8 issued guidelines to recruitment personnel in order to enlist transgender applicants by Jan. 1. The memo outlined medical requirements and specified how the applicants’ sex would be identified and even which undergarments they would wear. The Trump administration previously said in legal papers that the armed forces were not prepared to train thousands of personnel on the medical standards needed to process transgender applicants and might have to accept “some individuals who are not medically fit for service.” The Obama administration had set a deadline of July 1, 2017, to begin accepting transgender recruits. But Trump’s defense secretary, James Mattis, postponed that date to Jan. 1, 2018, which the president’s ban then put off indefinitely. Trump has taken other steps aimed at rolling back transgender rights. In October, his administration said a federal law banning gender-based workplace discrimination does not protect transgender employees, reversing another Obama-era position. In February, Trump rescinded guidance issued by the Obama administration saying that public schools should allow transgender students to use the restroom that corresponds to their gender identity. '


df_cleaned["text_stemmed"].iloc[1]

'washington - transgend peopl will be allow for the first time to enlist in the u.s. militari start on monday as order by feder courts, the pentagon said on friday, after presid donald trump’ administr decid not to appeal rule that block hi transgend ban. two feder appeal courts, one in washington and one in virginia, last week reject the administration’ request to put on hold order by lower court judg requir the militari to begin accept transgend recruit on jan. 1. a justic depart offici said the administr will not challeng those rulings. “the depart of defens ha announc that it will be releas an independ studi of these issu in the come weeks. so rather than litig thi interim appeal befor that occurs, the administr ha decid to wait for dod’ studi and will continu to defend the president’ law author in district court in the meantime,” the offici said, speak on condit of anonymity. in september, the pentagon said it had creat a panel of senior offici to studi how to implement a direct by trump to prohibit transgend individu from serving. the defens depart ha until feb. 21 to submit a plan to trump. lawyer repres currently-serv transgend servic member and aspir recruit said they had expect the administr to appeal the rule to the conservative-major suprem court, but were hope that would not happen. pentagon spokeswoman heather babb said in a statement: “a mandat by court order, the depart of defens is prepar to begin access transgend applic for militari servic jan. 1. all applic must meet all access standards.” jennif levi, a lawyer with gay, lesbian and transgend advocaci group glad, call the decis not to appeal “great news.” “i’m hope it mean the govern ha come to see that there is no way to justifi a ban and that it’ not good for the militari or our country,” levi said. both glad and the american civil liberti union repres plaintiff in the lawsuit file against the administration. in a move that appeal to hi hard-lin conserv supporters, trump announc in juli that he would prohibit transgend peopl from serv in the military, revers democrat presid barack obama’ polici of accept them. trump said on twitter at the time that the militari “cannot be burden with the tremend medic cost and disrupt that transgend in the militari would entail.” four feder judg - in baltimore, washington, d.c., seattl and riverside, california - have issu rule block trump’ ban while legal challeng to the republican president’ polici proceed. the judg said the ban would like violat the right under the u.s. constitut to equal protect under the law. the pentagon on dec. 8 issu guidelin to recruit personnel in order to enlist transgend applic by jan. 1. the memo outlin medic requir and specifi how the applicants’ sex would be identifi and even which undergar they would wear. the trump administr previous said in legal paper that the arm forc were not prepar to train thousand of personnel on the medic standard need to process transgend applic and might have to accept “some individu who are not medic fit for service.” the obama administr had set a deadlin of juli 1, 2017, to begin accept transgend recruits. but trump’ defens secretary, jame mattis, postpon that date to jan. 1, 2018, which the president’ ban then put off indefinitely. trump ha taken other step aim at roll back transgend rights. in october, hi administr said a feder law ban gender-bas workplac discrimin doe not protect transgend employees, revers anoth obama-era position. in february, trump rescind guidanc issu by the obama administr say that public school should allow transgend student to use the restroom that correspond to their gender identity.'


# Split the dataset into training and testing sets
train_data, test_data, train_labels, test_labels = train_test_split(df_cleaned['text_stemmed'], df_cleaned['fake'], test_size=0.2, random_state=15)

# Create a TF-IDF vectorizer to convert text into numerical features
vectorizer = TfidfVectorizer(max_features=5000, stop_words='english')
train_features = vectorizer.fit_transform(train_data)
test_features = vectorizer.transform(test_data)

# Train a decision tree classifier
tree_model = DecisionTreeClassifier()
tree_model.fit(train_features, train_labels)

# Extract feature names from the vectorizer
feature_names = vectorizer.get_feature_names_out()

# Visualize the decision tree
tree.plot_tree(tree_model, feature_names=feature_names)

# Get the most important features for classification
importance = tree_model.feature_importances_
important_features = [(feature_names[i], importance[i]) for i in range(len(feature_names))]
important_features.sort(key=lambda x: x[1], reverse=True)

# Print the top 10 important features
print("Top 10 important features:")
for feature, importance in important_features[:10]:
    print(f"{feature}: {importance}")

Top 10 important features:
said: 0.36124274622280655
th: 0.1721453257137617
imag: 0.13947697039839485
thi: 0.024336756121572507
com: 0.016880920457508365
https: 0.014588657466668521
washington: 0.010993220478723352
featur: 0.010899856336458196
minist: 0.01075947759642547
watch: 0.010046320346391833


pred = tree_model.predict(test_features)

loc_test_labels = test_labels.reset_index()
sum_correct = 0
for i in range(0, len(pred)-1):
    if pred[i] == loc_test_labels["fake"][i]:
        sum_correct += 1


sum_correct / len(pred) # 94.9% items predicted positively in total

0.9511082138200783


from sklearn.model_selection import cross_val_score


# Create a TF-IDF vectorizer to convert text into numerical features
vectorizer = TfidfVectorizer(max_features=5000, stop_words='english')
X = vectorizer.fit_transform(df_cleaned["text_stemmed"])
y = df_cleaned["fake"]

# Train a decision tree classifier using 5-fold-cross-validation
tree_model = DecisionTreeClassifier()
scores = cross_val_score(tree_model, X, y, cv=5)

# Print the cross-validation accuracy scores
print("Cross-Validation Accuracy Scores:")
for fold, score in enumerate(scores, start=1):
    print(f"Fold {fold}: {score}")

Cross-Validation Accuracy Scores:
Fold 1: 0.9469361147327249
Fold 2: 0.9498044328552803
Fold 3: 0.9311603650586702
Fold 4: 0.9183726691876385
Fold 5: 0.9205893858390924


scores.mean()

0.9333725935346813


# Create a TF-IDF vectorizer to convert text into numerical features
vectorizer = TfidfVectorizer(max_features=10000, stop_words='english')
X = vectorizer.fit_transform(df_cleaned["text_stemmed"])
y = df_cleaned["fake"]

# Train a decision tree classifier using 5-fold-cross-validation
tree_model = DecisionTreeClassifier()
scores = cross_val_score(tree_model, X, y, cv=5)

# Print the cross-validation accuracy scores
print("Cross-Validation Accuracy Scores:")
for fold, score in enumerate(scores, start=1):
    print(f"Fold {fold}: {score}")
    
    
print("Average Accuracy: ", scores.mean())

Cross-Validation Accuracy Scores:
Fold 1: 0.9569752281616688
Fold 2: 0.9494132985658409
Fold 3: 0.9246414602346805
Fold 4: 0.919285434867649
Fold 5: 0.920067805450515
Average Accuracy:  0.9340766454560707


# Create a TF-IDF vectorizer to convert text into numerical features
vectorizer = TfidfVectorizer(max_features=50000, stop_words='english')
X = vectorizer.fit_transform(df_cleaned["text_stemmed"])
y = df_cleaned["fake"]

# Train a decision tree classifier using 5-fold-cross-validation
tree_model = DecisionTreeClassifier()
scores = cross_val_score(tree_model, X, y, cv=5)

# Print the cross-validation accuracy scores
print("Cross-Validation Accuracy Scores:")
for fold, score in enumerate(scores, start=1):
    print(f"Fold {fold}: {score}")
    
    
print("Average Accuracy: ", scores.mean())

Cross-Validation Accuracy Scores:
Fold 1: 0.9550195567144719
Fold 2: 0.9491525423728814
Fold 3: 0.926857887874837
Fold 4: 0.913287260399009
Fold 5: 0.9217629417133916
Average Accuracy:  0.9332160378149181


# Create a TF-IDF vectorizer to convert text into numerical features
vectorizer = TfidfVectorizer(max_features=5000, stop_words='english', ngram_range=(2, 2))
X = vectorizer.fit_transform(df_cleaned["text_stemmed"])
y = df_cleaned["fake"]

# Train a decision tree classifier using 5-fold-cross-validation
tree_model = DecisionTreeClassifier()
scores = cross_val_score(tree_model, X, y, cv=5)

# Print the cross-validation accuracy scores
print("Cross-Validation Accuracy Scores:")
for fold, score in enumerate(scores, start=1):
    print(f"Fold {fold}: {score}")
    
    
print("Average Accuracy: ", scores.mean())

Cross-Validation Accuracy Scores:
Fold 1: 0.9466753585397654
Fold 2: 0.8955671447196871
Fold 3: 0.8934810951760104
Fold 4: 0.873516755769983
Fold 5: 0.8590428999869605
Average Accuracy:  0.8936566508384812


# Create a TF-IDF vectorizer to convert text into numerical features
vectorizer = TfidfVectorizer(max_features=5000, stop_words='english', ngram_range=(3, 3))
X = vectorizer.fit_transform(df_cleaned["text_stemmed"])
y = df_cleaned["fake"]

# Train a decision tree classifier using 5-fold-cross-validation
tree_model = DecisionTreeClassifier()
scores = cross_val_score(tree_model, X, y, cv=5)

# Print the cross-validation accuracy scores
print("Cross-Validation Accuracy Scores:")
for fold, score in enumerate(scores, start=1):
    print(f"Fold {fold}: {score}")
    
    
print("Average Accuracy: ", scores.mean())

Cross-Validation Accuracy Scores:
Fold 1: 0.8928292046936115
Fold 2: 0.8148631029986962
Fold 3: 0.8284224250325946
Fold 4: 0.8354413874038337
Fold 5: 0.8126222454035729
Average Accuracy:  0.8368356731064619


# Create a TF-IDF vectorizer to convert text into numerical features
vectorizer = TfidfVectorizer(max_features=5000, stop_words='english', ngram_range=(4, 4))
X = vectorizer.fit_transform(df_cleaned["text_stemmed"])
y = df_cleaned["fake"]

# Train a decision tree classifier using 5-fold-cross-validation
tree_model = DecisionTreeClassifier()
scores = cross_val_score(tree_model, X, y, cv=5)

# Print the cross-validation accuracy scores
print("Cross-Validation Accuracy Scores:")
for fold, score in enumerate(scores, start=1):
    print(f"Fold {fold}: {score}")
    
    
print("Average Accuracy: ", scores.mean())

Cross-Validation Accuracy Scores:
Fold 1: 0.8447196870925684
Fold 2: 0.7940026075619296
Fold 3: 0.7646675358539765
Fold 4: 0.7469031164428217
Fold 5: 0.7426000782370583
Average Accuracy:  0.7785786050376708


# Create a TF-IDF vectorizer to convert text into numerical features
vectorizer = TfidfVectorizer(max_features=5000, stop_words='english', ngram_range=(1, 4))
X = vectorizer.fit_transform(df_cleaned["text_stemmed"])
y = df_cleaned["fake"]

# Train a decision tree classifier using 5-fold-cross-validation
tree_model = DecisionTreeClassifier()
scores = cross_val_score(tree_model, X, y, cv=5)

# Print the cross-validation accuracy scores
print("Cross-Validation Accuracy Scores:")
for fold, score in enumerate(scores, start=1):
    print(f"Fold {fold}: {score}")
    
    
print("Average Accuracy: ", scores.mean())

Cross-Validation Accuracy Scores:
Fold 1: 0.9440677966101695
Fold 2: 0.8984354628422425
Fold 3: 0.9319426336375489
Fold 4: 0.913678445690442
Fold 5: 0.9158951623418959
Average Accuracy:  0.9208039002244599


#Best Model so far!

# Split the dataset into training and testing sets
train_data, test_data, train_labels, test_labels = train_test_split(df_cleaned['text_stemmed'], df_cleaned['fake'], test_size=0.2, random_state=15)

# Create a TF-IDF vectorizer to convert text into numerical features
vectorizer = TfidfVectorizer(max_features=5000, stop_words='english')
train_features = vectorizer.fit_transform(train_data)
test_features = vectorizer.transform(test_data)

# Train a decision tree classifier
tree_model = DecisionTreeClassifier()
tree_model.fit(train_features, train_labels)

# Extract feature names from the vectorizer
feature_names = vectorizer.get_feature_names_out()

# Visualize the decision tree
tree.plot_tree(tree_model, feature_names=feature_names)

# Get the most important features for classification
importance = tree_model.feature_importances_
important_features = [(feature_names[i], importance[i]) for i in range(len(feature_names))]
important_features.sort(key=lambda x: x[1], reverse=True)

# Print the top 10 important features
print("Top 10 important features:")
for feature, importance in important_features[:10]:
    print(f"{feature}: {importance}")

Top 10 important features:
said: 0.3613277828063353
th: 0.17198717529726557
imag: 0.13947697039839485
thi: 0.023923389424487344
com: 0.016880920457508365
https: 0.014223935510835683
washington: 0.010960272475286654
minist: 0.010935200281421182
featur: 0.010899856336458196
watch: 0.01026647291480976


pred = tree_model.predict(test_features)

loc_test_labels = test_labels.reset_index()
sum_correct = 0
for i in range(0, len(pred)-1):
    if pred[i] == loc_test_labels["fake"][i]:
        sum_correct += 1


sum_correct / len(pred) # 95.2% items predicted positively in total

0.9517601043024772


from matplotlib import pyplot as plt
fig, axes = plt.subplots(nrows = 1,ncols = 1,figsize = (30,30), dpi=600)
tree.plot_tree(tree_model, filled=True, feature_names=feature_names)
plt.savefig('tree.png', dpi=600)
plt.show()


test_data[8232]

'new york - donald trump declar on wednesday that russia’ vladimir putin had been a better leader than u.s. presid barack obama, as the republican presidenti nomine use a televis forum to argu he wa best equip to reassert america’ global leadership. trump suggest at the event in which he and democrat rival hillari clinton made back-to-back appear that u.s. gener had been stymi by the polici of obama and clinton, who serv as the democrat president’ first secretari of state. “i think under the leadership of barack obama and hillari clinton the gener have been reduc to rubble. they have been reduc to a point that’ embarrass for our country,” trump said at nbc’ “commander-in-chief” forum in new york attend by militari veterans. it wa the first time trump and clinton had squar off on the same stage sinc accept their parties’ presidenti nomin in juli for the nov. 8 election. clinton wa grill over her handl of classifi inform while use a privat email server dure her tenur at the state department. fbi director jame comey had declar her “extrem careless” in her handl of sensit materi but did not recommend charg against her. “i did exactli what i should have done and i take it veri seriously, alway have, alway will,” she said.trump’ prais of putin and hi suggest that the unit state and russia form an allianc to defeat islam state milit could rais eyebrow among foreign polici expert who feel moscow is interf with effort to stem the syrian civil war. “if he say great thing about me, i’m go to say great thing about him,” trump said of the russian president. “certainli in that system, he’ been a leader, far more than our presid ha been.” trump had call obama “the founder of isis,” an acronym for islam state, in stump speech sever week ago. the statement drew broad criticism, prompt him to take a more disciplin approach to campaigning. he ha sinc pick up ground on clinton in nation opinion polls. trump also flirt with reveal what he had been learn in classifi intellig brief given to him by u.s. offici becaus he is the republican nominee. “there wa one thing that shock me,” trump said. “what i did learn is that our leadership, barack obama, did not follow what our expert ... said to do, and i wa very, veri surprised. ...our leader were not follow what they recommended.” earlier on wednesday, trump pledg to launch a new u.s. militari buildup, say america wa under threat like never befor from foe like islamist extremists, north korea and china. the event offer a prelud to how clinton and trump will deal with question on nation secur issu in their three upcom presidenti debat later in septemb and in october. clinton began the forum say her long experi in govern as a u.s. senat and secretari of state made her uniqu qualifi to serv as president. she said she had “an absolut rock steadiness” to be abl to make tough decisions, a not so subtl dig at trump, who democrat say is temperament unfit for the white house. moder matt lauer doggedli press her about her handl of email from a privat server while secretari of state from 2009 to 2013. the issu ha rais question about whether she can be trust to serv as president. clinton said none of the email she sent or receiv were mark top secret, secret or classified, the usual way such materi is identified. appear in the second half of the hour-long show, trump face question about hi fit for office. ask if he would be prepar on day one to be command in chief, trump said: “one hundr percent.” trump quickli abandon lauer’ entreati to avoid attack hi oppon and focu on what he would do if elect presid in november. “she’ been there for 30 years,” trump said. “we need change, and we need it fast.” the event brought togeth the meticul prepar clinton, 68, the wife of former presid bill clinton, and trump, 70, a new york businessman whose brash, freewheel style ha allow him to domin the headlin dure hi campaign. clinton said she regret her decis as a u.s. senat from new york to vote in favor of the much-critic 2003 iraq war and that trump had been in favor of it as well. trump ha condemn the war dure hi campaign and said he would avoid lengthi conflict in the middl east. on the u.s. intervent in libya in 2011, clinton reject trump’ critic of her support for the effort as secretari of state. “permit there to be an ongo civil war in libya would be as threaten and as danger as what we are see in syria,” she said. trump said clinton’ handl of libya prove disastrous. republican have made much of the fact that the u.s. ambassador to libya, chri stevens, wa kill in an islamist attack in benghazi, libya, in 2012. “she made a terribl mistak in libya,” said trump. clinton said u.s. polici under her leadership at the state depart had help promot security. “we made the world safer,” she said.'


print(test_features[0])

  (0, 35)	0.04808872773051405
  (0, 41)	0.04013522497697604
  (0, 43)	0.03850084434050053
  (0, 44)	0.03515658570186762
  (0, 45)	0.03556124969086618
  (0, 71)	0.031482235510104956
  (0, 115)	0.05172944953379566
  (0, 117)	0.04106598582655754
  (0, 134)	0.04349846118999503
  (0, 143)	0.030728138071455056
  (0, 150)	0.03474201847174634
  (0, 159)	0.0331720549924528
  (0, 245)	0.03016442970954729
  (0, 281)	0.04174231216569779
  (0, 285)	0.025222406818486965
  (0, 293)	0.0676129980676364
  (0, 296)	0.03749581960914753
  (0, 301)	0.04850264006562163
  (0, 357)	0.0525913956603475
  (0, 365)	0.03664933994080295
  (0, 380)	0.03462630570335908
  (0, 403)	0.022196761245201285
  (0, 432)	0.048922865351767056
  (0, 435)	0.03490436801466689
  (0, 467)	0.07033644908727302
  :	:
  (0, 4550)	0.01782057367880211
  (0, 4559)	0.03496105576688818
  (0, 4580)	0.038603681848526694
  (0, 4644)	0.32116097700980184
  (0, 4645)	0.03843295076684736
  (0, 4702)	0.051614460217132486
  (0, 4711)	0.051576463510497945
  (0, 4712)	0.01932643051458175
  (0, 4732)	0.047521893599842796
  (0, 4743)	0.04079801302394682
  (0, 4745)	0.039210400378089906
  (0, 4774)	0.04515675771372111
  (0, 4783)	0.054008025321505046
  (0, 4813)	0.03839920033146977
  (0, 4819)	0.02293406312585752
  (0, 4827)	0.08053518068821988
  (0, 4841)	0.108063831097098
  (0, 4862)	0.021616551055479404
  (0, 4875)	0.048023702740727425
  (0, 4876)	0.020589801354013677
  (0, 4898)	0.02105611168409977
  (0, 4903)	0.036614926430348985
  (0, 4946)	0.024008593707264155
  (0, 4976)	0.02774573378634365
  (0, 4983)	0.10779853296321389


tree_model.predict(test_features[0])

array([0])


len(feature_names) #This is 5000 long because we established max_features = 5000

5000


feature_names

array(['00', '000', '10', ..., 'zone', 'zor', 'zuma'], dtype=object)


print(tree_model.decision_path(test_features[0]))

  (0, 0)	1
  (0, 648)	1
  (0, 649)	1
  (0, 650)	1
  (0, 651)	1
  (0, 652)	1
  (0, 653)	1
  (0, 654)	1
  (0, 655)	1
  (0, 656)	1
  (0, 657)	1
  (0, 658)	1
  (0, 659)	1
  (0, 660)	1
  (0, 661)	1
  (0, 662)	1
  (0, 663)	1
  (0, 664)	1
  (0, 665)	1
  (0, 666)	1
  (0, 667)	1
  (0, 668)	1
  (0, 669)	1
  (0, 670)	1
  (0, 671)	1
  :	:
  (0, 756)	1
  (0, 757)	1
  (0, 758)	1
  (0, 759)	1
  (0, 760)	1
  (0, 761)	1
  (0, 762)	1
  (0, 763)	1
  (0, 764)	1
  (0, 765)	1
  (0, 766)	1
  (0, 767)	1
  (0, 768)	1
  (0, 769)	1
  (0, 770)	1
  (0, 771)	1
  (0, 772)	1
  (0, 773)	1
  (0, 774)	1
  (0, 775)	1
  (0, 776)	1
  (0, 777)	1
  (0, 778)	1
  (0, 779)	1
  (0, 780)	1


n_nodes = tree_model.tree_.node_count
children_left = tree_model.tree_.children_left
children_right = tree_model.tree_.children_right
feature = tree_model.tree_.feature
threshold = tree_model.tree_.threshold

X_test = test_features


node_indicator = tree_model.decision_path(X_test)
leaf_id = tree_model.apply(X_test)

sample_id = 2
# obtain ids of the nodes `sample_id` goes through, i.e., row `sample_id`
node_index = node_indicator.indices[
    node_indicator.indptr[sample_id] : node_indicator.indptr[sample_id + 1]
]

print("Rules used to predict sample {id}:\n".format(id=sample_id))
for node_id in node_index:
    # continue to the next node if it is a leaf node
    if leaf_id[sample_id] == node_id:
        continue

    # check if value of the split feature for sample 0 is below threshold
    if X_test[sample_id, feature[node_id]] <= threshold[node_id]:
        threshold_sign = "<="
    else:
        threshold_sign = ">"

    print(
        "decision node {node} : (X_test[{sample}, {feature}] = {value}) "
        "{inequality} {threshold})".format(
            node=node_id,
            sample=sample_id,
            feature=feature[node_id],
            value=X_test[sample_id, feature[node_id]],
            inequality=threshold_sign,
            threshold=threshold[node_id],
        )
    )

Rules used to predict sample 2:

decision node 0 : (X_test[2, 3909] = 0.08257088598465868) > 0.03112895507365465)
decision node 648 : (X_test[2, 4509] = 0.0) <= 0.004100584425032139)
decision node 649 : (X_test[2, 2244] = 0.0) <= 0.02063043136149645)
decision node 650 : (X_test[2, 2199] = 0.0) <= 0.007333007175475359)
decision node 651 : (X_test[2, 4764] = 0.0) <= 0.035441914573311806)
decision node 652 : (X_test[2, 1358] = 0.0) <= 0.038928279653191566)
decision node 653 : (X_test[2, 3344] = 0.0) <= 0.04044116474688053)
decision node 654 : (X_test[2, 1985] = 0.0) <= 0.03848862834274769)
decision node 655 : (X_test[2, 4055] = 0.0) <= 0.015775397419929504)
decision node 656 : (X_test[2, 1485] = 0.0) <= 0.017427759245038033)
decision node 657 : (X_test[2, 3634] = 0.0) <= 0.04243004880845547)
decision node 658 : (X_test[2, 4894] = 0.0) <= 0.010134678333997726)
decision node 659 : (X_test[2, 2493] = 0.0) <= 0.06964515894651413)
decision node 660 : (X_test[2, 3738] = 0.0) <= 0.0507810153067112)
decision node 661 : (X_test[2, 232] = 0.0) <= 0.016683651134371758)
decision node 662 : (X_test[2, 1090] = 0.0) <= 0.06726432964205742)
decision node 663 : (X_test[2, 769] = 0.0) <= 0.017349570989608765)
decision node 664 : (X_test[2, 1959] = 0.0) <= 0.01268040295690298)
decision node 665 : (X_test[2, 1137] = 0.0) <= 0.05931176617741585)
decision node 666 : (X_test[2, 4856] = 0.0) <= 0.03959180973470211)
decision node 667 : (X_test[2, 355] = 0.0) <= 0.01828521490097046)
decision node 668 : (X_test[2, 2148] = 0.0) <= 0.1901034712791443)
decision node 669 : (X_test[2, 4182] = 0.0) <= 0.05524014122784138)
decision node 670 : (X_test[2, 2073] = 0.0) <= 0.08285689726471901)
decision node 671 : (X_test[2, 709] = 0.0) <= 0.02678176946938038)
decision node 672 : (X_test[2, 2524] = 0.0) <= 0.058523016050457954)
decision node 673 : (X_test[2, 4955] = 0.0) <= 0.0655912458896637)
decision node 674 : (X_test[2, 2658] = 0.05010618757302066) <= 0.15058037638664246)
decision node 675 : (X_test[2, 2735] = 0.0) <= 0.06458630785346031)
decision node 676 : (X_test[2, 1920] = 0.0) <= 0.07530393078923225)
decision node 677 : (X_test[2, 2960] = 0.0) <= 0.11118507385253906)
decision node 678 : (X_test[2, 3974] = 0.0) <= 0.040849439799785614)
decision node 679 : (X_test[2, 3565] = 0.0) <= 0.0705627016723156)
decision node 680 : (X_test[2, 742] = 0.0) <= 0.10862131416797638)
decision node 681 : (X_test[2, 1119] = 0.0) <= 0.037847088649868965)
decision node 682 : (X_test[2, 708] = 0.0) <= 0.09091030433773994)
decision node 683 : (X_test[2, 677] = 0.0) <= 0.11146101728081703)
decision node 684 : (X_test[2, 3618] = 0.0) <= 0.06239195354282856)
decision node 685 : (X_test[2, 858] = 0.0) <= 0.21910104900598526)
decision node 686 : (X_test[2, 4786] = 0.0) <= 0.2799434959888458)
decision node 687 : (X_test[2, 3240] = 0.0) <= 0.2579064592719078)
decision node 688 : (X_test[2, 4054] = 0.0) <= 0.41695553064346313)
decision node 689 : (X_test[2, 4064] = 0.0) <= 0.27712124586105347)
decision node 690 : (X_test[2, 1564] = 0.0) <= 0.35001419484615326)
decision node 691 : (X_test[2, 131] = 0.0) <= 0.11184950545430183)
decision node 692 : (X_test[2, 1799] = 0.0) <= 0.023648111149668694)
decision node 693 : (X_test[2, 3289] = 0.0) <= 0.6188528835773468)
decision node 694 : (X_test[2, 1743] = 0.07470436825094597) <= 0.1328761950135231)
decision node 695 : (X_test[2, 733] = 0.0) <= 0.07040472328662872)
decision node 696 : (X_test[2, 530] = 0.0) <= 0.2118307650089264)
decision node 697 : (X_test[2, 2965] = 0.0) <= 0.10029597207903862)
decision node 698 : (X_test[2, 2125] = 0.0) <= 0.0889420434832573)
decision node 699 : (X_test[2, 2779] = 0.0) <= 0.27493709325790405)
decision node 700 : (X_test[2, 1037] = 0.0) <= 0.3406751751899719)
decision node 701 : (X_test[2, 1326] = 0.0) <= 0.18150590360164642)
decision node 702 : (X_test[2, 121] = 0.0) <= 0.12437033280730247)
decision node 703 : (X_test[2, 271] = 0.0) <= 0.07590512186288834)
decision node 704 : (X_test[2, 1855] = 0.0) <= 0.29999177157878876)
decision node 705 : (X_test[2, 2963] = 0.0) <= 0.16315537691116333)
decision node 706 : (X_test[2, 2800] = 0.0) <= 0.08704488351941109)
decision node 707 : (X_test[2, 4009] = 0.0) <= 0.044869232922792435)
decision node 708 : (X_test[2, 4651] = 0.0) <= 0.6769784390926361)
decision node 709 : (X_test[2, 4637] = 0.0) <= 0.2396111637353897)
decision node 710 : (X_test[2, 2299] = 0.0) <= 0.33450592309236526)
decision node 711 : (X_test[2, 2236] = 0.0) <= 0.2921052575111389)
decision node 712 : (X_test[2, 1439] = 0.0) <= 0.20616884157061577)
decision node 713 : (X_test[2, 3531] = 0.0) <= 0.21827290952205658)
decision node 714 : (X_test[2, 3118] = 0.06198541761786403) <= 0.22246916592121124)
decision node 715 : (X_test[2, 2190] = 0.0) <= 0.3856894075870514)
decision node 716 : (X_test[2, 3822] = 0.0) <= 0.30308666825294495)
decision node 717 : (X_test[2, 2304] = 0.0) <= 0.2595519423484802)
decision node 718 : (X_test[2, 3795] = 0.0) <= 0.465387761592865)
decision node 719 : (X_test[2, 2739] = 0.0) <= 0.38565194606781006)
decision node 720 : (X_test[2, 1165] = 0.0) <= 0.24729330092668533)
decision node 721 : (X_test[2, 901] = 0.0) <= 0.08920750766992569)
decision node 722 : (X_test[2, 4915] = 0.0) <= 0.36934812366962433)
decision node 723 : (X_test[2, 3133] = 0.0) <= 0.23777402937412262)
decision node 724 : (X_test[2, 3399] = 0.059269623923076456) <= 0.25794798135757446)
decision node 725 : (X_test[2, 3309] = 0.0) <= 0.3814828395843506)
decision node 726 : (X_test[2, 1981] = 0.0) <= 0.2419453263282776)
decision node 727 : (X_test[2, 3529] = 0.0) <= 0.3781767413020134)
decision node 728 : (X_test[2, 2881] = 0.0) <= 0.47116148471832275)
decision node 729 : (X_test[2, 2683] = 0.0) <= 0.27298273146152496)
decision node 730 : (X_test[2, 3466] = 0.0) <= 0.5025071501731873)
decision node 731 : (X_test[2, 4391] = 0.0) <= 0.22987641394138336)
decision node 732 : (X_test[2, 4893] = 0.0) <= 0.1964850127696991)
decision node 733 : (X_test[2, 875] = 0.0) <= 0.24781974405050278)
decision node 734 : (X_test[2, 573] = 0.0) <= 0.23447566106915474)
decision node 735 : (X_test[2, 3235] = 0.0) <= 0.6826426982879639)
decision node 736 : (X_test[2, 316] = 0.0) <= 0.24823792278766632)
decision node 737 : (X_test[2, 4827] = 0.05193740068873335) <= 0.2624070942401886)
decision node 738 : (X_test[2, 3408] = 0.0) <= 0.2446560636162758)
decision node 739 : (X_test[2, 3670] = 0.0) <= 0.4789866805076599)
decision node 740 : (X_test[2, 952] = 0.0) <= 0.23744390532374382)
decision node 741 : (X_test[2, 849] = 0.0) <= 0.2791730463504791)
decision node 742 : (X_test[2, 878] = 0.0) <= 0.4723604619503021)
decision node 743 : (X_test[2, 4525] = 0.03325251020874442) <= 0.34229470789432526)
decision node 744 : (X_test[2, 453] = 0.0) <= 0.5746106803417206)
decision node 745 : (X_test[2, 52] = 0.0) <= 0.03588072583079338)
decision node 746 : (X_test[2, 1495] = 0.0) <= 0.5142679810523987)
decision node 747 : (X_test[2, 2899] = 0.0) <= 0.2235613614320755)
decision node 748 : (X_test[2, 2485] = 0.0) <= 0.2314666137099266)
decision node 749 : (X_test[2, 3724] = 0.0) <= 0.19017504155635834)
decision node 750 : (X_test[2, 738] = 0.0) <= 0.3433455228805542)
decision node 751 : (X_test[2, 2438] = 0.0) <= 0.0835178792476654)
decision node 752 : (X_test[2, 667] = 0.0) <= 0.0697844997048378)
decision node 753 : (X_test[2, 3986] = 0.0) <= 0.2876126170158386)
decision node 754 : (X_test[2, 852] = 0.0) <= 0.14642544090747833)
decision node 755 : (X_test[2, 1921] = 0.0) <= 0.11007019877433777)
decision node 756 : (X_test[2, 2748] = 0.0) <= 0.17178154736757278)
decision node 757 : (X_test[2, 1829] = 0.0) <= 0.2751568853855133)
decision node 758 : (X_test[2, 3479] = 0.0) <= 0.15366841107606888)
decision node 759 : (X_test[2, 610] = 0.0) <= 0.4208744913339615)
decision node 760 : (X_test[2, 2852] = 0.0) <= 0.14081858098506927)
decision node 761 : (X_test[2, 3665] = 0.0) <= 0.3083181232213974)
decision node 762 : (X_test[2, 1446] = 0.0) <= 0.38813072443008423)
decision node 763 : (X_test[2, 2798] = 0.0) <= 0.7539668381214142)
decision node 764 : (X_test[2, 1651] = 0.0) <= 0.19380173832178116)
decision node 765 : (X_test[2, 1912] = 0.0) <= 0.07279519364237785)
decision node 766 : (X_test[2, 3317] = 0.0) <= 0.5230422019958496)
decision node 767 : (X_test[2, 1934] = 0.0) <= 0.35934072732925415)
decision node 768 : (X_test[2, 640] = 0.0) <= 0.10842181742191315)
decision node 769 : (X_test[2, 4060] = 0.0) <= 0.13149722665548325)
decision node 770 : (X_test[2, 3336] = 0.0) <= 0.28887443244457245)
decision node 771 : (X_test[2, 2210] = 0.0) <= 0.4919208586215973)
decision node 772 : (X_test[2, 4494] = 0.0) <= 0.08604681864380836)
decision node 773 : (X_test[2, 781] = 0.0) <= 0.44687725603580475)
decision node 774 : (X_test[2, 1318] = 0.0) <= 0.12311891466379166)
decision node 775 : (X_test[2, 2202] = 0.0) <= 0.08503024652600288)
decision node 776 : (X_test[2, 1333] = 0.0) <= 0.21778281778097153)
decision node 777 : (X_test[2, 2219] = 0.0) <= 0.054079363122582436)
decision node 778 : (X_test[2, 4366] = 0.0) <= 0.11365454643964767)
decision node 779 : (X_test[2, 1976] = 0.0) <= 0.07552583888173103)


import pydotplus

dot_data = tree.export_graphviz(tree_model, out_file=None,
                                feature_names=feature_names,
                                filled=True, rounded=True,
                                special_characters=True)
graph = pydotplus.graph_from_dot_data(dot_data)

samples = X_test[514]
decision_paths = tree_model.decision_path(samples)

for decision_path in decision_paths:
    for n, node_value in enumerate(decision_path.toarray()[0]):
        if node_value == 0:
            continue
        node = graph.get_node(str(n))[0]            
        node.set_fillcolor('green')
        labels = node.get_attributes()['label'].split('<br/>')
        for i, label in enumerate(labels):
            if label.startswith('samples = '):
                labels[i] = 'samples = {}'.format(int(label.split('=')[1]) + 1)

        node.set('label', '<br/>'.join(labels))


import graphviz
from IPython.display import Image
graph.write_png("decision_path_highlighted.png")
Image(graph.create_png())


test_data[514]

'washington - presid donald trump said there wa a “pocahontas” in the u.s. congress dure a meet on monday with nativ american world war two veteran in an appar derogatori refer to democrat senat elizabeth warren of massachusetts. after listen to one veteran speak at length about hi experi as a “navajo code talker” dure the war, trump heap prais on the veteran and said he would not give prepar remark himself. “you were here long befor ani of us were here,” trump said. “although we have a repres in congress who they say wa here a long time ago. they call her pocahontas.” trump repeatedli refer to warren as “pocahontas,” the name of a famou 17th-centuri nativ american, dure hi presidenti campaign in a mock refer to warren’ have said in the past that she had nativ american ancestry. warren, one of the senate’ most promin liber democrats, is a note legal scholar who taught at harvard law school and serv as an advis to former presid barack obama befor she wa elect to the senat in 2012. “it is deepli unfortun that the presid of the unit state cannot even make it through a ceremoni honor these hero without have to throw out a racial slur,” warren said on msnbc. white hous spokeswoman sarah sander disput the character of trump’ remark as a racial slur. “i think what most peopl find offens is senat warren lie about her heritag to advanc her career,” sander told reporters. jefferson keel, presid of the nation congress of american indians, question the “use of the name pocahonta as a slur ... onc again, we call upon the presid to refrain from use her name in a way that denigr her legacy.” trump’ comment immedi trend on social media. the word “pocahontas” appear 12 time on twitter everi second, accord to social media analyt compani zoomph. trump’ knock at warren came as hi administr is embroil in controversi over the consum financi protect board, which warren help develop befor enter politics. the agency, set up to protect american from abus lend practic after the financi crisis, ha been under attack by trump sinc he took offic in january. on friday, trump name hi budget director as the interim head of the agency, after it outgo chief name someon els to the job, set up a court battle.'


test_labels[514]

0


import pydotplus

dot_data = tree.export_graphviz(tree_model, out_file=None,
                                feature_names=feature_names,
                                filled=True, rounded=True,
                                special_characters=True)
graph = pydotplus.graph_from_dot_data(dot_data)

samples = X_test[700]
decision_paths = tree_model.decision_path(samples)

for decision_path in decision_paths:
    for n, node_value in enumerate(decision_path.toarray()[0]):
        if node_value == 0:
            continue
        node = graph.get_node(str(n))[0]            
        node.set_fillcolor('green')
        labels = node.get_attributes()['label'].split('<br/>')
        for i, label in enumerate(labels):
            if label.startswith('samples = '):
                labels[i] = 'samples = {}'.format(int(label.split('=')[1]) + 1)

        node.set('label', '<br/>'.join(labels))


import graphviz
from IPython.display import Image
graph.write_png("decision_path_highlighted_2.png")
Image(graph.create_png())


test_data[700]

'- a tax plan by u.s. senat republican releas on thursday diverg in sever way from legisl be push by republican in the hous of representatives, complic republican effort to fulfil their goal of overhaul the tax code by the end of the year. here are the major provis that differ significantly. corpor rate: the hous plan would immedi cut the corpor incom tax rate to 20 percent from 35 percent. the senat would set the same rate, but delay it by one year. carri interest: the senat leav unchang a loophol that allow private-equ fund manag and other wealthi wall street financi to pay the capit gain tax rate instead of the higher incom tax rate on their “carri interest” income. the hous version narrow the loophol by requir invest to be held for more than three year instead of one year current in order to qualifi for capit gain treatment. net oper losses: the senat version elimin the carry-back and carry-forward tax strategi by busi to reduc past and futur tax liabil use net oper losses. the hous version tighten the rule around their use. pass-throughs: the hous cap the maximum tax rate on small busi and other non-corpor enterpris at 25 percent, down from the current top rate on “pass-through” incom of up to 39.6 percent. the senat version ha no special pass-through rate but allow busi owner to deduct about 17.4 percent of busi incom from individu taxes. that translat to a 30 percent tax rate for high-incom filers. repatri of oversea earnings: the senat impos a tax of 12 percent for liquid asset and 5 percent for illiquid. the hous set the rate at 14 percent and 7 percent, respectively. tax brackets: the senat version maintain seven tax brackets, with the top bracket’ rate at 38.5 percent. the hous ha four bracket with the top one unchang from current level at 39.6 percent and lift qualifi incom on that top rate to more than $1 million. mortgag interest deduction: the hous cap the deduct of interest payment on mortgag of up to $500,000, and onli on a primari residence. the senat version keep the exist limit at $1 million but elimin the deduct of interest on home-equ loans. deduct state and local taxes: the senat bill repeal the state and local tax deduct entirely. the hous version repeal the deduct for state and local incom and sale tax and cap the deduct for state and local properti tax paid at $10,000. standard deduction: the two version are in line with each other, with a standard deduct of $12,200 for individu and $24,000 for marri couples, nearli doubl the current levels. child tax credit: the senat would expand the child tax credit to $1,650 from $1,000. the hous version set it at $1,600. inheritances: while the hous want to doubl the exempt on inherit asset and repeal the tax over a period of six years, the senat onli want to doubl the exemption.'


test_labels[700]

0


#!wget https://www.cs.ucsb.edu/~william/data/liar_dataset.zip


#!unzip -o liar_dataset.zip


LIAR_train = pd.read_csv('train.tsv', sep='\t', header=None)


LIAR_test = pd.read_csv('test.tsv', sep='\t', header=None)


LIAR = pd.concat([LIAR_train, LIAR_test])


LIAR


LIAR = LIAR.iloc[:, :8]


LIAR.rename(columns = {0:'ID_politifact', 1:'label', 2:'statement', 3:'subjects', 4:'speaker', 5:'speakers_job_title', 6:'state_info', 7:'party_affiliation'}, inplace = True)


LIAR


LIAR["label"].unique()

array(['false', 'half-true', 'mostly-true', 'true', 'barely-true',
       'pants-fire'], dtype=object)


true_labels = ['true', 'half-true', 'mostly-true']


LIAR["label_binary"] = LIAR["label"].apply(lambda x: 0 if x in true_labels else 1)


LIAR["statement_len"] = LIAR["statement"].apply(len)


LIAR["statement_len"].describe()

count    11507.000000
mean       107.211610
std         65.214163
min         11.000000
25%         73.000000
50%         99.000000
75%        133.000000
max       3192.000000
Name: statement_len, dtype: float64


stemmer = PorterStemmer()

LIAR["statement_stemmed"] = LIAR['statement'].apply(lambda x: ' '.join([stemmer.stem(word) for word in x.split()]))


# Split the dataset into training and testing sets
train_data, test_data, train_labels, test_labels = train_test_split(LIAR['statement_stemmed'], LIAR['label_binary'], test_size=0.2, random_state=15)

# Create a TF-IDF vectorizer to convert text into numerical features
vectorizer = TfidfVectorizer(max_features=5000, stop_words='english')
train_features = vectorizer.fit_transform(train_data)
test_features = vectorizer.transform(test_data)

# Train a decision tree classifier
tree_model = DecisionTreeClassifier()
tree_model.fit(train_features, train_labels)

# Extract feature names from the vectorizer
feature_names = vectorizer.get_feature_names_out()

# Visualize the decision tree
tree.plot_tree(tree_model, feature_names=feature_names)

# Get the most important features for classification
importance = tree_model.feature_importances_
important_features = [(feature_names[i], importance[i]) for i in range(len(feature_names))]
important_features.sort(key=lambda x: x[1], reverse=True)

# Print the top 10 important features
print("Top 10 important features:")
for feature, importance in important_features[:10]:
    print(f"{feature}: {importance}")

Top 10 important features:
say: 0.018189496979688476
obama: 0.013026348725617674
wa: 0.012403158065717906
percent: 0.011899122573521576
state: 0.009885203269722394
vote: 0.009867915030541638
ha: 0.008471470475084017
billion: 0.007214896020876925
wisconsin: 0.005885762084695842
years: 0.00585075349544118


pred = tree_model.predict(test_features)

loc_test_labels = test_labels.reset_index()
sum_correct = 0
for i in range(0, len(pred)-1):
    if pred[i] == loc_test_labels["label_binary"][i]:
        sum_correct += 1


sum_correct / len(pred) #

0.552997393570808


#Best Model so far!

# Split the dataset into training and testing sets
train_data, test_data, train_labels, test_labels = train_test_split(df_cleaned['text_stemmed'], df_cleaned['fake'], test_size=0.2, random_state=15)

# Create a TF-IDF vectorizer to convert text into numerical features
vectorizer = TfidfVectorizer(max_features=5000, stop_words='english')
train_features = vectorizer.fit_transform(train_data)
test_features = vectorizer.transform(test_data)

# Train a decision tree classifier
tree_model = DecisionTreeClassifier()
tree_model.fit(train_features, train_labels)

# Extract feature names from the vectorizer
feature_names = vectorizer.get_feature_names_out()

# Visualize the decision tree
tree.plot_tree(tree_model, feature_names=feature_names)

# Get the most important features for classification
importance = tree_model.feature_importances_
important_features = [(feature_names[i], importance[i]) for i in range(len(feature_names))]
important_features.sort(key=lambda x: x[1], reverse=True)

# Print the top 10 important features
print("Top 10 important features:")
for feature, importance in important_features[:10]:
    print(f"{feature}: {importance}")

Top 10 important features:
said: 0.36123678420313704
th: 0.17198717529726557
imag: 0.13947697039839485
thi: 0.02411082695514944
com: 0.016650284433451484
https: 0.014223935510835681
featur: 0.01107557902145391
washington: 0.01089437646841326
minist: 0.01075947759642547
watch: 0.010376299592932082


LIAR_set = LIAR["statement_stemmed"]
LIAR_label = LIAR["label_binary"]


test_features_LIAR = vectorizer.transform(LIAR_set)


pred = tree_model.predict(test_features_LIAR)

loc_test_labels = LIAR_label.reset_index()
sum_correct = 0
for i in range(0, len(pred)-1):
    if pred[i] == loc_test_labels["label_binary"][i]:
        sum_correct += 1


sum_correct / len(pred) #

0.4769270878595637

	title	text	subject	date
0	Donald Trump Sends Out Embarrassing New Year’...	Donald Trump just couldn t wish all Americans ...	News	December 31, 2017
1	Drunk Bragging Trump Staffer Started Russian ...	House Intelligence Committee Chairman Devin Nu...	News	December 31, 2017
2	Sheriff David Clarke Becomes An Internet Joke...	On Friday, it was revealed that former Milwauk...	News	December 30, 2017
3	Trump Is So Obsessed He Even Has Obama’s Name...	On Christmas day, Donald Trump announced that ...	News	December 29, 2017
4	Pope Francis Just Called Out Donald Trump Dur...	Pope Francis used his annual Christmas Day mes...	News	December 25, 2017
...	...	...	...	...
23476	McPain: John McCain Furious That Iran Treated ...	21st Century Wire says As 21WIRE reported earl...	Middle-east	January 16, 2016
23477	JUSTICE? Yahoo Settles E-mail Privacy Class-ac...	21st Century Wire says It s a familiar theme. ...	Middle-east	January 16, 2016
23478	Sunnistan: US and Allied ‘Safe Zone’ Plan to T...	Patrick Henningsen 21st Century WireRemember ...	Middle-east	January 15, 2016
23479	How to Blow $700 Million: Al Jazeera America F...	21st Century Wire says Al Jazeera America will...	Middle-east	January 14, 2016
23480	10 U.S. Navy Sailors Held by Iranian Military ...	21st Century Wire says As 21WIRE predicted in ...	Middle-east	January 12, 2016

	title	text	subject	date	fake
0	Donald Trump Sends Out Embarrassing New Year’...	Donald Trump just couldn t wish all Americans ...	News	December 31, 2017	True
1	Drunk Bragging Trump Staffer Started Russian ...	House Intelligence Committee Chairman Devin Nu...	News	December 31, 2017	True
2	Sheriff David Clarke Becomes An Internet Joke...	On Friday, it was revealed that former Milwauk...	News	December 30, 2017	True
3	Trump Is So Obsessed He Even Has Obama’s Name...	On Christmas day, Donald Trump announced that ...	News	December 29, 2017	True
4	Pope Francis Just Called Out Donald Trump Dur...	Pope Francis used his annual Christmas Day mes...	News	December 25, 2017	True
...	...	...	...	...	...
23476	McPain: John McCain Furious That Iran Treated ...	21st Century Wire says As 21WIRE reported earl...	Middle-east	January 16, 2016	True
23477	JUSTICE? Yahoo Settles E-mail Privacy Class-ac...	21st Century Wire says It s a familiar theme. ...	Middle-east	January 16, 2016	True
23478	Sunnistan: US and Allied ‘Safe Zone’ Plan to T...	Patrick Henningsen 21st Century WireRemember ...	Middle-east	January 15, 2016	True
23479	How to Blow $700 Million: Al Jazeera America F...	21st Century Wire says Al Jazeera America will...	Middle-east	January 14, 2016	True
23480	10 U.S. Navy Sailors Held by Iranian Military ...	21st Century Wire says As 21WIRE predicted in ...	Middle-east	January 12, 2016	True

	title	text	subject	date	fake
0	As U.S. budget fight looms, Republicans flip t...	WASHINGTON (Reuters) - The head of a conservat...	politicsNews	December 31, 2017	False
1	U.S. military to accept transgender recruits o...	WASHINGTON (Reuters) - Transgender people will...	politicsNews	December 29, 2017	False
2	Senior U.S. Republican senator: 'Let Mr. Muell...	WASHINGTON (Reuters) - The special counsel inv...	politicsNews	December 31, 2017	False
3	FBI Russia probe helped by Australian diplomat...	WASHINGTON (Reuters) - Trump campaign adviser ...	politicsNews	December 30, 2017	False
4	Trump wants Postal Service to charge 'much mor...	SEATTLE/WASHINGTON (Reuters) - President Donal...	politicsNews	December 29, 2017	False
...	...	...	...	...	...
23476	McPain: John McCain Furious That Iran Treated ...	21st Century Wire says As 21WIRE reported earl...	Middle-east	January 16, 2016	True
23477	JUSTICE? Yahoo Settles E-mail Privacy Class-ac...	21st Century Wire says It s a familiar theme. ...	Middle-east	January 16, 2016	True
23478	Sunnistan: US and Allied ‘Safe Zone’ Plan to T...	Patrick Henningsen 21st Century WireRemember ...	Middle-east	January 15, 2016	True
23479	How to Blow $700 Million: Al Jazeera America F...	21st Century Wire says Al Jazeera America will...	Middle-east	January 14, 2016	True
23480	10 U.S. Navy Sailors Held by Iranian Military ...	21st Century Wire says As 21WIRE predicted in ...	Middle-east	January 12, 2016	True

	title	text	subject	date	fake
12655	VIRAL VIDEO: A Must Watch Video Hillary Doesn’...		politics	Oct 22, 2016	True
12800	HILLARY CLINTON RAPE ENABLER: “What kind of mo...		politics	Oct 8, 2016	True
12802	BREAKING: DONALD TRUMP Video Statement On Leak...		politics	Oct 8, 2016	True
12825	FUNNY! MSNBC ANCHOR ASKS Millennial Women If T...		politics	Oct 5, 2016	True
12831	A MUST SEE! MEDIA SCORCHED FOR THEIR BIAS AGAI...		politics	Oct 4, 2016	True
...	...	...	...	...	...
19548	CNN HOST To Jill Stein: “Have You Seen Any Dir...	https://youtu.be/E2KFe_htBSA And I think the f...	left-news	Nov 27, 2016	True
19524	THE VIEW’S Whoopi Goldberg To Co-Host: “This I...	https://youtu.be/RTuxvWjH3a4	left-news	Dec 1, 2016	True
19277	TEMPERS FLARE IN DC: BIKERS FOR TRUMP Break Th...	https://youtu.be/ZfRYj2ZX3dE#Trump supporter g...	left-news	Jan 20, 2017	True
19619	TRUMP SUPPORTER Whose Brutal Beating By Black ...	https://youtu.be/kKFQ5i9jXmA	left-news	Nov 14, 2016	True
19410	OHIO ELECTOR TORCHES Anti-Trump Letters He Rec...	pic.twitter.com/KMnLrwB6t1 Richard K. Jones (...	left-news	Dec 21, 2016	True

	title	text	subject	date	fake	text_length
0	As U.S. budget fight looms, Republicans flip t...	WASHINGTON (Reuters) - The head of a conservat...	politicsNews	December 31, 2017	False	4659
1	U.S. military to accept transgender recruits o...	WASHINGTON (Reuters) - Transgender people will...	politicsNews	December 29, 2017	False	4077
2	Senior U.S. Republican senator: 'Let Mr. Muell...	WASHINGTON (Reuters) - The special counsel inv...	politicsNews	December 31, 2017	False	2789
3	FBI Russia probe helped by Australian diplomat...	WASHINGTON (Reuters) - Trump campaign adviser ...	politicsNews	December 30, 2017	False	2461
4	Trump wants Postal Service to charge 'much mor...	SEATTLE/WASHINGTON (Reuters) - President Donal...	politicsNews	December 29, 2017	False	5204
...	...	...	...	...	...	...
23476	McPain: John McCain Furious That Iran Treated ...	21st Century Wire says As 21WIRE reported earl...	Middle-east	January 16, 2016	True	3237
23477	JUSTICE? Yahoo Settles E-mail Privacy Class-ac...	21st Century Wire says It s a familiar theme. ...	Middle-east	January 16, 2016	True	1684
23478	Sunnistan: US and Allied ‘Safe Zone’ Plan to T...	Patrick Henningsen 21st Century WireRemember ...	Middle-east	January 15, 2016	True	25065
23479	How to Blow $700 Million: Al Jazeera America F...	21st Century Wire says Al Jazeera America will...	Middle-east	January 14, 2016	True	2685
23480	10 U.S. Navy Sailors Held by Iranian Military ...	21st Century Wire says As 21WIRE predicted in ...	Middle-east	January 12, 2016	True	5251

Data Science and Artificial Intelligence II¶

Fake News detection project¶

by David Sitek and Nicola Krenn¶

Comparison with new dataset¶

	title	text	subject	date	fake
count	44898	44898	44898	44898	44898
unique	38729	38646	8	2397	2
top	Factbox: Trump fills top jobs for his administ...		politicsNews	December 20, 2017	True
freq	14	627	11272	182	23481

	title	text	subject	date	fake	text_length
13677	MUSLIM INVASION OF AMERICA In Full Swing: Obam...	(Welcome) to America We hope you enjoy our...	politics	Jun 17, 2016	True	2494
16547	MUSLIM INVASION OF AMERICA In Full Swing: Obam...	(Welcome) to America We hope you enjoy our...	Government News	Jun 17, 2016	True	2494
18505	WOW! MAJOR CREDIT CARD COMPANY Still Sponsorin...	Delta Air Lines and Bank of America became ...	left-news	Jun 12, 2017	True	1889
10645	WOW! MAJOR CREDIT CARD COMPANY Still Sponsorin...	Delta Air Lines and Bank of America became ...	politics	Jun 12, 2017	True	1889
16289	A MUST WATCH! “It’s Time To Show America Is Bi...	#PresidentElectTrumpABSOLUTELY MUST WATCHTod...	Government News	Dec 21, 2016	True	198
...	...	...	...	...	...	...
11234	BONKERS BERNIE SANDERS: Prioritizing Jobs Over...	https://www.youtube.com/watch?v=GPqQIlWksbgVer...	politics	Apr 1, 2017	True	1463
19548	CNN HOST To Jill Stein: “Have You Seen Any Dir...	https://youtu.be/E2KFe_htBSA And I think the f...	left-news	Nov 27, 2016	True	871
12285	CNN HOST To Jill Stein: “Have You Seen Any Dir...	https://youtu.be/E2KFe_htBSA And I think the f...	politics	Nov 27, 2016	True	871
19277	TEMPERS FLARE IN DC: BIKERS FOR TRUMP Break Th...	https://youtu.be/ZfRYj2ZX3dE#Trump supporter g...	left-news	Jan 20, 2017	True	405
11849	TEMPERS FLARE IN DC: BIKERS FOR TRUMP Break Th...	https://youtu.be/ZfRYj2ZX3dE#Trump supporter g...	politics	Jan 20, 2017	True	405

	title	text	date	fake	text_length
subject
politicsNews	11213	11213	11213	11213	11213
worldnews	9978	9978	9978	9978	9978

	title	text	subject	date	fake	text_length
0	As U.S. budget fight looms, Republicans flip t...	WASHINGTON - The head of a conservative Repub...	politicsNews	December 31, 2017	0	4659
1	U.S. military to accept transgender recruits o...	WASHINGTON - Transgender people will be allow...	politicsNews	December 29, 2017	0	4077
2	Senior U.S. Republican senator: 'Let Mr. Muell...	WASHINGTON - The special counsel investigatio...	politicsNews	December 31, 2017	0	2789
3	FBI Russia probe helped by Australian diplomat...	WASHINGTON - Trump campaign adviser George Pa...	politicsNews	December 30, 2017	0	2461
4	Trump wants Postal Service to charge 'much mor...	SEATTLE/WASHINGTON - President Donald Trump c...	politicsNews	December 29, 2017	0	5204
...	...	...	...	...	...	...
22698	The White House and The Theatrics of ‘Gun Cont...	21st Century Wire says All the world s a stage...	US_News	January 7, 2016	1	7359
22699	Activists or Terrorists? How Media Controls an...	Randy Johnson 21st Century WireThe majority ...	US_News	January 7, 2016	1	26275
22700	BOILER ROOM – No Surrender, No Retreat, Heads ...	Tune in to the Alternate Current Radio Network...	US_News	January 6, 2016	1	1150
22701	Federal Showdown Looms in Oregon After BLM Abu...	21st Century Wire says A new front has just op...	US_News	January 4, 2016	1	20651
22702	A Troubled King: Chicago’s Rahm Emanuel Desper...	21st Century Wire says It s not that far away....	US_News	January 2, 2016	1	5749

	0	1	2	3	4	5	6	7	8	9	10	11	12	13
0	2635.json	false	Says the Annies List political group supports ...	abortion	dwayne-bohac	State representative	Texas	republican	0.0	1.0	0.0	0.0	0.0	a mailer
1	10540.json	half-true	When did the decline of coal start? It started...	energy,history,job-accomplishments	scott-surovell	State delegate	Virginia	democrat	0.0	0.0	1.0	1.0	0.0	a floor speech.
2	324.json	mostly-true	Hillary Clinton agrees with John McCain "by vo...	foreign-policy	barack-obama	President	Illinois	democrat	70.0	71.0	160.0	163.0	9.0	Denver
3	1123.json	false	Health care reform legislation is likely to ma...	health-care	blog-posting	NaN	NaN	none	7.0	19.0	3.0	5.0	44.0	a news release
4	9028.json	half-true	The economic turnaround started at the end of ...	economy,jobs	charlie-crist	NaN	Florida	democrat	15.0	9.0	20.0	19.0	2.0	an interview on CNN
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
1262	7334.json	half-true	Says his budget provides the highest state fun...	education	rick-scott	Governor	Florida	republican	28.0	23.0	38.0	34.0	7.0	a news conference
1263	9788.json	barely-true	Ive been here almost every day.	civil-rights,crime,criminal-justice	jay-nixon	Governor	Missouri	democrat	2.0	0.0	0.0	1.0	0.0	on ABC's "This Week"
1264	10710.json	barely-true	In the early 1980s, Sen. Edward Kennedy secret...	bipartisanship,congress,foreign-policy,history	mackubin-thomas-owens	senior fellow, Foreign Policy Research Institute	Rhode Island	columnist	1.0	0.0	0.0	0.0	0.0	a commentary in The Providence Journal
1265	3186.json	barely-true	Says an EPA permit languished under Strickland...	environment,government-efficiency	john-kasich	Governor of Ohio as of Jan. 10, 2011	Ohio	republican	9.0	8.0	10.0	18.0	3.0	a news conference
1266	6743.json	false	Says the governor is going around the state ta...	state-budget,state-finances,taxes	john-burzichelli	NaN	NaN	democrat	1.0	1.0	0.0	0.0	0.0	an interview with NJToday

	title	text	date	fake	text_length
subject
Government News	498	498	498	498	498
News	9050	9050	9050	9050	9050
US_News	783	783	783	783	783
left-news	663	663	663	663	663
politics	6163	6163	6163	6163	6163